AgentGarten：代码环境与实时神经渲染结合的智能体演化平台
Overview
MirroS团队发布了AgentGarten，一个将可执行代码环境与帧率超过30fps的实时神经渲染器结合起来的智能体训练框架，让智能体能够行动、观察并从中学习。据量子位报道，在一对一捉迷藏实验中，躲藏者在第4轮学会封堵通道，寻找者在第10轮学会爬坡，且两者都依据每轮后自己撰写的笔记进行调整。作者称同一循环还被应用于另外四类任务，包括陪伴小狗、窄桥会车、放牧和装载采石等，但报道中并未给出这些任务的具体结果数据。
Written by AI from the articles below · updated Oct 8, 10:56 PM ET
Check the sources:
Article timeline
Follow the coverage from different perspectives. Times are ET.
- QbitAIAgentGarten lets agents evolve through code-built worlds and neural rendering
AIMirroS released AgentGarten, which pairs executable code environments with a real-time neural renderer running above 30 fps so agents can act, observe, and learn. In a one-on-one hide-and-seek setup, the hider learned to block passages by round 4 and the seeker learned to climb ramps by round 10, guided by notes the agents wrote after each round. The authors report applying the same loop to four other tasks, including a dog-companion game, a narrow-bridge car passing task, herding, and quarry loading.
Heat trend
Not enough continuous observations to show a trend yet.